Coding agents on cloud machines with a record of every session
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Free trial
Pricing
Not given
Free trial: two machines, up to 2 vCPU and 4 GiB. Cuna Inference pricing: models available at varying rates, such as GLM-5.2 at $1.00 per million input tokens and $4.00 per million output tokens.
Key features
Start teams with one command and manage agents across multiple machines
Mix Claude Code, Codex and Pi agents in one team
Agents delegate and coordinate work with named task assignments and queue ownership
Agents message each other directly and read each other's screens
Restore agent conversations after restart or reboot from snapshots
Choose different models and reasoning effort per agent
Bring custom harnesses and integrate with MCP servers and Claude Desktop
Start Docker Compose services alongside agent teams
Control message filtering with typing guards and chat broadcasts
Isolated session execution with bounded authority
Web console for machine management
Complete action recording and visibility
OpenAI-compatible Chat Completions API
OpenCuna terminal agent
Multiple model provider support
Cuna Memory for agent state persistence
Token-based pay-as-you-go pricing
What makes it different
One conversation interface with a lead agent coordinating specialists behind the scenes
Mix multiple coding models and harnesses in one managed team
Run entirely self-hosted on your own machine with no external coordination
Open source with Apache 2.0 license and extensible harness contracts
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency